{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_bb7b63eb39807f0cd21a30cd039bc22dfb516033e62ce6c9bf46df07cad8182d","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_bb7b63eb39807f0cd21a30cd039bc22dfb516033e62ce6c9bf46df07cad8182d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"c0ab0033290702dd5a17cea230b9830a44df36cbe1bbe3a312ae4dc2b2614074","published":"Wed, 08 Jul 2026 00:00:00 -0400","receipt_hash":"c0ab0033290702dd5a17cea230b9830a44df36cbe1bbe3a312ae4dc2b2614074","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"c0ab0033290702dd5a17cea230b9830a44df36cbe1bbe3a312ae4dc2b2614074","observed_at":"2026-07-08T04:43:57.834712Z","parent_run_hash":"46ab019f0b0f0bfcde5e14ed7c256069c6fa8c8079b9f87fd3a8a6d9259e3864","published":"Wed, 08 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2506.09276v4 Announce Type: replace-cross \nAbstract: This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally enables critical downstream tasks such as goal-conditioned reinforcement learning and reward shaping by providing a dense, geometrically meaningful measure of progress. Our self-supervised learning approach constructs an embedding space where the distances between embedded state pairs correspond to their MAD, accommodating both symmetric and asymmetric approximations. We evaluate the framework on a comprehensive suite of environments with known MAD values, encompassing both deterministic and","title":"Learning The Minimum Action Distance","url":"https://arxiv.org/abs/2506.09276","vendor":"arxiv_cs_ai"},"summary":"arXiv:2506.09276v4 Announce Type: replace-cross \nAbstract: This paper presents a state representation framework for Markov decision processes (MDPs) that can be learned solely from state trajectories, requiring neither reward signals nor the actions executed by the agent. We propose learning the minimum action distance (MAD), defined as the minimum number of actions required to transition between states, as a fundamental metric that captures the underlying structure of an environment. MAD naturally enables critical downstream tasks such as goal-conditioned reinforcement learning and reward shaping by providing a dense, geometrically meaningful measure of progress. Our self-supervised learning approach constructs an embedding space where the distances between embedded state pairs correspond to their MAD, accommodating both symmetric and asymmetric approximations. We evaluate the framework on a comprehensive suite of environments with known MAD values, encompassing both deterministic and","title":"Learning The Minimum Action Distance","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-08T04:43:57Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2506.09276"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:32ade53db96c6a0e07a19665b55a235264676162325272c792dad53a96681a618260813f23fcd562d9b71478643cb3f8f7485f8a96568ac59f51d744122b1408","signer":"crovia.substrate","subject":{"observed_at":"2026-07-08T04:43:57Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2506.09276"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"2335fec56917458595c4d2192e6437a41a4a39d8591024136723815ac1dd70c7","leaf_index":292824,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"212116f98d95b9d588ce45056fce6cbe7ed0ae5c52f90d67b0ee85f56d46c657","side":"right"},{"sibling":"5e3ea102724effc502239f32e62d985c3c8fad51673e7886920138be00665d78","side":"right"},{"sibling":"30f46706c9a8689a712217255255decdea6552637180e9021723440d3ffa6c20","side":"right"},{"sibling":"29950c52761a253b7be868cd3432603aaeee0ee2d0a35f25d9b5b03bbe337028","side":"left"},{"sibling":"31f4dfbaae9b09fc2d0bd6cb58bdc5d16596af80c369510977ac46c54f633a25","side":"left"},{"sibling":"c3bcd80d31f44b45ac24d75235b431952a5fbdf53c2994e96b08aa35f6212442","side":"right"},{"sibling":"b68effed96c9c760c6a644ba421552cb75cab0f5269153819ebc6ee58c6e16f1","side":"left"},{"sibling":"6e4b9570930ece9a9ba8eab260493982ccceb0060de1dddb4ef505f9f3d00598","side":"left"},{"sibling":"1515812edbf9903d3d787f20218b8577e2f1fef32592508ce01a3b3ebe75f507","side":"left"},{"sibling":"d4b475beae71e5b4d5ab7e66f7144e7b8e1356fcd32339e49df234b455659fef","side":"left"},{"sibling":"cead64e0790e8871aeea2334210146b5e35fe7e4bc10748acdf76da0c565be05","side":"left"},{"sibling":"d1231ac6e6bd7d6867a9109fbdadede0b1631e97866ddde70f7ac2d52c28e15f","side":"right"},{"sibling":"76855b4804c75c52bf97aa34358950d42d6103cdc1a86be5f0a2c8de4d65c106","side":"left"},{"sibling":"a75ab4319e241beeddb1b3f5705febe0422937926c3479923ccfb0b0082fa4e3","side":"left"},{"sibling":"bd04fa605f883bfb2b81510d045b1e85e555a03da3be083619f61384dfe40ff8","side":"left"},{"sibling":"9e75f2ab0ddf2dc9e92af7049244c21b909734ab57906a35dfad2853ca9966e2","side":"right"},{"sibling":"e6cd4cad39a4b6ca6647d1b0ad2db86e57e5fa6240f65966c10093e91140769b","side":"right"},{"sibling":"90a7efc6b94ec8913fbdf03f4927a821b9fb89921d526716f5ee28f015303779","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":292998,"merkle_root":"f533b7efebdfd8fb6ba3e7cc158ee55261fd53a7985f234cfea359170dad4d5a","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260708T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-08T05:38:17Z","sig_algorithm":"ed25519","signature":"07ebb10c732bbffb28b55a5db01d5525f6b8ab7ef36e1e0a68c35c96ded99f7040c277edba75eb6b15c77feda30bd5321e31ada6f572b674d06f4f8e24bd2f07","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_bb7b63eb39807f0cd21a30cd039bc22dfb516033e62ce6c9bf46df07cad8182d"}}